Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tensor stress

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “tensor” (particularly in phrases like “energy-momentum tensor” or “stress tensor”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    acters
    -0.06
    Erot
    -0.06
    rier
    -0.06
     DTO
    -0.06
    乱
    -0.06
    rons
    -0.06
    role
    -0.06
    istas
    -0.06
     antim
    -0.06
     مست
    -0.06
    POSITIVE LOGITS
     peter
    0.07
    _SCHEDULE
    0.07
     tường
    0.07
     Jenny
    0.07
    .stack
    0.07
    .py
    0.06
    Practice
    0.06
    _il
    0.06
     forget
    0.06
    のに
    0.06
    Act Density 0.013%

    No Known Activations